Cross-modal unsupervised domain adaptation (UDA) aims to transfer segmentation models trained on a labeled source modality to an unlabeled target modality. However, existing methods often fail to fully exploit shape priors and intermediate feature representations, resulting in limited generalization ability of the model in cross-modal transfer tasks. To address this challenge, we propose a segmentation model based on shape-aware adaptive weighting (SAWS) that enhance the model's ability to perceive the target area and capture global and local information. Specifically, we design a multi-angle strip-shaped shape perception (MSSP) module that captures shape features from multiple orientations through an angular pooling strategy, improving structural modeling under cross-modal settings. In addition, an adaptive weighted hierarchical contrastive (AWHC) loss is introduced to fully leverage intermediate features and enhance segmentation accuracy for small target structures. The proposed method is evaluated on the multi-modality whole heart segmentation (MMWHS) dataset. Experimental results demonstrate that SAWS achieves superior performance in cross-modal cardiac segmentation tasks, with a Dice score (Dice) of 70.1% and an average symmetric surface distance (ASSD) of 4.0 for the computed tomography (CT)→magnetic resonance imaging (MRI) task, and a Dice of 83.8% and ASSD of 3.7 for the MRI→CT task, outperforming existing state-of-the-art methods. Overall, this study proposes a cross-modal medical image segmentation method with shape-aware, which effectively improves the structure-aware ability and generalization performance of the UDA model.
To accurately capture and address the multi-dimensional feature variations in cross-subject motor imagery electroencephalogram (MI-EEG), this paper proposes a time-frequency transform and Riemannian manifold based domain adaptation network (TFRMDANet) in a high-dimensional brain source space. Source imaging technology was employed to reconstruct neural electrical activity and compute regional cortical dipoles, and the multi-subband time-frequency feature data were constructed via wavelet transform. The two-stage multi-branch time–frequency–spatial feature extractor with squeeze-and-excitation (SE) modules was designed to extract local features and cross-scale global features from each subband, and the channel attention and multi-scale feature fusion were introduced simultaneously for feature enhancement. A Riemannian manifold embedding-based structural feature extractor was used to capture high-order discriminative features, while adversarial training promoted domain-invariant feature learning. Experiments on public BCI Competition IV dataset 2a and High-Gamma dataset showed that TFRMDANet achieved classification accuracies of 77.82% and 90.47%, with Kappa values of 0.704 and 0.826, and F1-scores of 0.780 and 0.905, respectively. The results demonstrate that cortical dipoles provide accurate time–frequency representations of MI features, and the unique multi-branch architecture along with its strong time–frequency–spatial–structural feature extraction capability enables effective domain adaptation enhancement in brain source space.
The research shows that personality assessment can be achieved by regression model based on electroencephalogram (EEG). Most of existing researches use event-related potential or power spectral density for personality assessment, which can only represent the brain information of a single region. But some research shows that human cognition is more dependent on the interaction of brain regions. In addition, due to the distribution difference of EEG features among subjects, the trained regression model can not get accurate results of cross subject personality assessment. In order to solve the problem, this research proposes a personality assessment method based on EEG functional connectivity and domain adaption. This research collected EEG data from 45 normal people under different emotional pictures (positive, negative and neutral). Firstly, the coherence of 59 channels in 5 frequency bands was taken as the original feature set. Then the feature-based domain adaptation was used to map the feature to a new feature space. It can reduce the distribution difference between training and test set in the new feature space, so as to reduce the distribution difference between subjects. Finally, the support vector regression model was trained and tested based on the transformed feature set by leave-one-out cross-validation. What’s more, this paper compared the methods used in previous researches. The results showed that the method proposed in this paper improved the performance of regression model and obtained better personality assessment results. This research provides a new method for personality assessment.